ABSTRACT
Current research into automatic generation of semantic descriptions centers mainly on improving the annotation accuracy for individual tag or attributes. In this paper, we focus on the generation of more informative descriptions for images. We proposes to generate layered, semantically meaningful descriptions and create summaries of key aspects of the data from the component detectors. In particular, the output descriptions include superclass, class, attributes, and the location of the area of the object which may interest users. We propose to integrate ROI (Region of Interest) identification and hierarchical semantic elements detection into a joint framework. The joint optimization of the ROI localizer and the hierarchical concept detection make them mutually beneficial and reciprocal. In this way, we create a discriminative image description generation framework based on a tightly coupled multi-layer optimization. The output descriptions contain richer information of the image content with layered contextual information, thereby enabling better management and usage of image data. Experiments on two public open benchmark datasets demonstrate that the proposed method obtains state of the art performance.
- U. Brefeld, T. Gärtner, T. Scheffer, and S. Wrobel. Efficient co-regularised least squares regression. In NIPS, pages 137--144, 2006. Google ScholarDigital Library
- X. Cai, F. Nie, H. Huang, and C. H. Ding. Multi-class ℓ2,1-norm support vector machine. In IEEE International Conference on Data Mining, pages 91--100, 2011. Google ScholarDigital Library
- K. Crammer and Y. Singer. On the algorithmic implementation of multiclass kernel-based vector machines. The Journal of Machine Learning Research, 2:265--292, 2002. Google ScholarDigital Library
- D. Ding, F. Metze, S. Rawat, P. F. Schulam, S. Burger, E. Younessian, L. Bao, M. G. Christel, and A. Hauptmann. Beyond audio and video retrieval: towards multimedia summarization. In Proceedings of the 2012 ACM International Conference on Multimedia Retrieval, 2012. Google ScholarDigital Library
- A. Farhadi, I. Endres, D. Hoiem, and D. Forsyth. Describing objects by their attributes. In CVPR, pages 1778--1785, 2009.Google ScholarCross Ref
- A. Farhadi, M. Hejrati, M. Sadeghi, P. Young, C. Rashtchian, J. Hockenmaier, and D. Forsyth. Every picture tells a story: Generating sentences from images. ECCV, pages 15--29, 2010. Google ScholarDigital Library
- T. Fawcett. An introduction to roc analysis. Pattern recognition letters, 27(8):861--874, 2006. Google ScholarDigital Library
- Y. Gong, S. Lazebnik, A. Gordo, and F. Perronnin. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012. Google ScholarDigital Library
- S. Guadarrama, N. Krishnamoorthy, G. Malkarnenkar, S. Venugopalan, R. Mooney, T. Darrell, and K. Saenko. Youtube2text: Recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In ICCV, pages 2712--2719. IEEE, 2013. Google ScholarDigital Library
- A. Hauptmann, R. Yan, W.-H. Lin, M. Christel, and H. Wactlar. Can high-level concepts fill the semantic gap in video retrieval? a case study with broadcast news. IEEE Transactions on Multimedia, 9(5):958--966, 2007. Google ScholarDigital Library
- G. Kulkarni, V. Premraj, S. Dhar, S. Li, Y. Choi, A. C. Berg, and T. L. Berg. Baby talk: Understanding and generating simple image descriptions. In CVPR, pages 1601--1608, 2011. Google ScholarDigital Library
- X. Liu, Y. Mu, B. Lang, and S.-F. Chang. Compact hashing for mixed image-keyword query over multi-label images. In ACM Multimedia, page 18, 2012. Google ScholarDigital Library
- Z. Ma, F. Nie, Y. Yang, J. R. Uijlings, and N. Sebe. Web image annotation via subspace-sparsity collaborated feature selection. IEEE Transactions on Multimedia, 14(4):1021--1030, 2012. Google ScholarDigital Library
- Z. Ma, Y. Yang, Y. Cai, N. Sebe, and A. G. Hauptmann. Knowledge adaptation for ad hoc multimedia event detection with few exemplars. In ACM Multimedia, pages 469--478, 2012. Google ScholarDigital Library
- F. Nie, H. Huang, X. Cai, and C. H. Ding. Efficient and robust feature selection via joint ℓ2,1-norms minimization. NIPS, 23:1813--1821, 2010.Google Scholar
- D. Parikh and K. Grauman. Relative attributes. In ICCV, pages 503--510, 2011. Google ScholarDigital Library
- C. Pollard and I. A. Sag. Head-driven phrase structure grammar. University of Chicago Press, 1994.Google Scholar
- C. Wang, S. Yan, L. Zhang, and H.-J. Zhang. Multi-label sparse coding for automatic image annotation. In CVPR, pages 1643--1650, 2009.Google ScholarCross Ref
- S.-I. Yu, Z. Xu, D. Ding, W. Sze, F. Vicente, Z. Lan, Y. Cai, S. Rawat, P. Schulam, S. Bahmani, et al. Informedia e-lamp@ trecvid 2012 multimedia event detection and recounting (med and mer). 2012.Google Scholar
- D. Zhang, M. M. Islam, and G. Lu. A review on automatic image annotation techniques. Pattern Recognition, 45(1):346--362, 2012. Google ScholarDigital Library
- D. Zhou, J. Huang, and B. Scholkopf. Learning with hypergraphs: Clustering, classification, and embedding. NIPS, 19:1601, 2007.Google Scholar
Index Terms
- Describing Images with Hierarchical Concepts and Object Class Localization
Recommendations
Medical image describing behavior: a comparison between an expert and novice
iConference '11: Proceedings of the 2011 iConferenceThis preliminary study, as a part of a broader study about the medical image use by experts and novices, examines the differences in image describing behavior between these two categories of users. Eye tracking technique was used to capture the image ...
Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing
ICCV '13: Proceedings of the 2013 IEEE International Conference on Computer VisionIn recent years, there has been a great deal of progress in describing objects with attributes. Attributes have proven useful for object recognition, image search, face verification, image description, and zero-shot learning. Typically, attributes are ...
Rotation invariant HOG for object localization in web images
To localize objects in Web images using an invariant descriptor is crucial. The HOG (histogram of oriented gradients) descriptor is used to increase the accuracy of localization. It is a shape descriptor that considers frequencies of gradient ...
Comments